Update app.py

app.py

@@ -2,68 +2,58 @@ import os
 import spaces
 import gradio as gr
 from huggingface_hub import InferenceClient
+from pydantic import BaseModel
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 HF_TOKEN = os.getenv("HF_TOKEN")
 
-model_name = "HuggingFaceH4/zephyr-7b-beta"
-client = InferenceClient(model_name, api_key=HF_TOKEN)
-
-@spaces.GPU(duration=60)
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+class PaperAnalysis(BaseModel):
+    title: str
+    abstract_summary: str
+
+response_format = {
+    "type": "json_schema",
+    "json_schema": {
+        "name": "PaperAnalysis",
+        "schema": PaperAnalysis.model_json_schema(),
+        "strict": True,
+    },
+}
+
+client = InferenceClient(
+    provider="auto",
+    api_key=HF_TOKEN,
 )
 
+@spaces.GPU(duration=60)
+def extract_info(paper_text: str):
+    if not paper_text.strip():
+        return {"title": "", "abstract_summary": ""}
+    messages = [
+        {"role": "system", "content": "Extract the paper title and summarize its abstract."},
+        {"role": "user", "content": paper_text},
+    ]
+    resp = client.chat.completions.create(
+        model="meta-llama/Llama-3.2-1B-Instruct",
+        messages=messages,
+        response_format=response_format,
+    )
+    # parse response
+    parsed = resp.choices[0].message
+    # assuming the message is a dict
+    return {
+        "title": parsed.content.get("title", ""),
+        "abstract_summary": parsed.content.get("abstract_summary", ""),
+    }
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🎓 Paper Analysis Tool")
+    with gr.Row():
+        paper_input = gr.Textbox(label="Paper Text (include Title/Abstract)", lines=10)
+        with gr.Column():
+            title_out = gr.Textbox(label="Title", lines=1)
+            summary_out = gr.Textbox(label="Abstract Summary", lines=5)
+    analyze_btn = gr.Button("Extract Info")
+    analyze_btn.click(fn=extract_info, inputs=paper_input, outputs=[title_out, summary_out])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()